Fuzzy Support Vector Machines Based on Convex Hulls

Abstract

Fast fuzzy support vector machines (FFSVMs) based on the convex hulls are proposed in this paper. Firstly, the convex hull of each class data is generated by using the quick hull algorithm, and the data points lying inside the convex hull are not important to form FSVMs and then discarded. Secondly, the reduced training set consisting of the convex points is used to train the FFSVMs. Thirdly, the benchmark two-class problems and multi-class problems datasets are used to test the effectiveness and validness of FFSVMs. The experiment results indicate that FFSVMs not only reduce the training set but also achieve the same or better performance compared with the traditional FSVMs.